CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

musa: update compile flags (#16265)

Browse Source 
Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>
This commit is contained in:
R0CKSTAR
2025-10-02 21:29:56 +08:00
committed by GitHub
parent 72ee736c44
commit 91a2a56556
3 changed files with 2 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/fattn-vec.cuh
View File

@@ -535,8 +535,6 @@ void ggml_cuda_flash_attn_ext_vec_case(ggml_backend_cuda_context & ctx, ggml_ten
float logit_softcap;
memcpy(&logit_softcap, (const float *) KQV->op_params + 2, sizeof(float));
const int cc = ggml_cuda_info().devices[ggml_cuda_get_device()].cc;
if (Q->ne[1] == 1) {
constexpr int cols_per_block = 1;
if (logit_softcap == 0.0f) {

4
ggml/src/ggml-cuda/topk-moe.cu
View File

@@ -13,7 +13,7 @@
It is intended as fusion of softmax->top-k->get_rows pipeline for MoE models
*/
template <size_t n_experts, bool with_norm>
template <int n_experts, bool with_norm>
__launch_bounds__(4 * WARP_SIZE, 1) __global__ void topk_moe_cuda(const float * logits,
float * weights,
int32_t * ids,
@@ -204,8 +204,6 @@ void ggml_cuda_op_topk_moe(ggml_backend_cuda_context & ctx,
GGML_ASSERT(ids->nb[1] / ggml_type_size(ids->type) == (size_t) n_experts);
cudaStream_t stream = ctx.stream();
const int n_expert_used = weights->ne[1];
if (with_norm) {

2
ggml/src/ggml-musa/CMakeLists.txt
View File

@@ -56,7 +56,7 @@ if (MUSAToolkit_FOUND)
set_source_files_properties(${GGML_SOURCES_MUSA} PROPERTIES LANGUAGE CXX)
foreach(SOURCE ${GGML_SOURCES_MUSA})
set(COMPILE_FLAGS "-fsigned-char -x musa -mtgpu")
set(COMPILE_FLAGS "-Od3 -fno-strict-aliasing -ffast-math -fsigned-char -x musa -mtgpu -fmusa-flush-denormals-to-zero")
foreach(ARCH ${MUSA_ARCHITECTURES})
set(COMPILE_FLAGS "${COMPILE_FLAGS} --cuda-gpu-arch=mp_${ARCH}")
endforeach()